# Mindee MCP by usefulapi

> Mindee MCP by usefulapi is an MCP server. Turn PDFs and images into typed fields — invoices, receipts, IDs and custom models — via Mindee OCR. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Website:** https://usefulapi.io/mindee/
- **Repository:** https://github.com/m190/usefulapi-mcp/tree/HEAD/servers/mindee
- **MCP Registry name:** io.usefulapi/mindee
- **Listing updated:** 2026-11-13

## About

Turn PDFs and images into typed fields — invoices, receipts, IDs and custom models — via Mindee OCR.

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http mindee https://mindee.usefulapi.io/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mindee.usefulapi.io/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "mindee": {
      "url": "https://mindee.usefulapi.io/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "mindee": {
      "type": "http",
      "url": "https://mindee.usefulapi.io/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "mindee": {
      "serverUrl": "https://mindee.usefulapi.io/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "mindee": {
      "type": "http",
      "url": "https://mindee.usefulapi.io/mcp"
    }
  }
}
```

## Tools

- `mindee_list_models`: List the document-extraction models available to your Mindee account (id, name, type). Use a model's `id` as the model_id for mindee_extract_document. V2 API: GET /v2/search/models.
- `mindee_get_job`: Check the processing status of an enqueued document by job id. Status is Waiting | Processing | Processed | Failed. When Processed, the response carries a result_url; pass that inference id to mindee_get_inference. V2 API: GET /v2/jobs/{job_id}.
- `mindee_get_inference`: Fetch the structured result of a completed inference by id, returned as a compact map of extracted fields (plus raw_text if it was requested). V2 API: GET /v2/inferences/{inference_id}.
- `mindee_extract_document`: Submit a document (PDF or image) to a Mindee extraction model and return the structured fields. Provide EITHER document_url (a public URL) OR file_base64 (+ filename). This enqueues an inference and polls until it completes (up to ~30s); if it is still processing it returns a job_id you can poll with mindee_get_job then read with mindee_get_inference. NOTE: consumes Mindee API credits (paid, bille

## FAQ

### How do I add Mindee MCP by usefulapi to Claude Code?

Run this command in your terminal: claude mcp add --transport http mindee https://mindee.usefulapi.io/mcp

---
Source: https://ai-powered.com/mcp/mindee-mcp-by-usefulapi
